Upload a file to the CNC controller
AI agents use upload_to_sd to create or update resources in Cnc Fluidnc — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Cnc Fluidnc environment.
This tool creates or stores new data on the CNC controller's SD card, making it a Write operation. Severity is high because malicious or corrupted uploads could cause the CNC machine to execute dangerous operations (collisions, incorrect cutting paths, safety violations), but the primary action is file storage rather than immediate execution.
From the tool's definition Tool uploads a file to the CNC controller's SD card storage. The description states 'Upload a file to the CNC controller', which is a write operation that modifies the controller's persistent storage.
Attacks that exploit this kind of access
Upload a file to the CNC controller. It is categorised as a Write tool in the Cnc Fluidnc MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Cnc Fluidnc MCP server in PolicyLayer and add a rule for upload_to_sd: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Cnc Fluidnc. Nothing to install.
upload_to_sd is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the upload_to_sd rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for upload_to_sd. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
upload_to_sd is provided by the Cnc Fluidnc MCP server (whitneydesignlabs/cnc-fluidnc-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →